{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:57:01Z","timestamp":1775120221757,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1564214"],"award-info":[{"award-number":["U1564214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61611540348"],"award-info":[{"award-number":["61611540348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/tie.2017.2708002","type":"journal-article","created":{"date-parts":[[2017,5,25]],"date-time":"2017-05-25T18:11:35Z","timestamp":1495735895000},"page":"9517-9526","source":"Crossref","is-referenced-by-count":16,"title":["Self-Learning Control Using Dual Heuristic Programming with Global Laplacian Eigenmaps"],"prefix":"10.1109","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"first","affiliation":[]},{"given":"Huiyuan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chuanqiang","family":"Lian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3777-0063","authenticated-orcid":false,"given":"Jiahang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.831130"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/science.295.5552.7a"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-012-9255-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1201\/b11431-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.880135"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/TNNLS.2013.2292704","article-title":"Reinforcement learning output feedback NN control using deterministic learning technique","volume":"25","author":"xu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2006.888760"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2344"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2246866"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref19","first-page":"1008","article-title":"Actor-critic algorithms","volume":"12","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"2169","article-title":"Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes","volume":"8","author":"mahadevan","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.08.037"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.07.008"},{"key":"ref5","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref8","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesvari","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2542134"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2314612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4757-2"},{"key":"ref24","first-page":"561","article-title":"Learning feature representations with K-means","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(84)90020-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/8082391\/07934056.pdf?arnumber=7934056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T21:50:16Z","timestamp":1659045016000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7934056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":36,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tie.2017.2708002","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}